Abstract
We examine the Bayes-consistency of a recently proposed 1-nearest-neighbor-based multiclass learning algorithm. This algorithm is derived from sample compression bounds and enjoys the statistical advantages of tight, fully empirical generalization bounds, as well as the algorithmic advantages of a faster runtime and memory savings. We prove that this algorithm is strongly Bayes-consistent in metric spaces with finite doubling dimension - the first consistency result for an efficient nearest-neighbor sample compression scheme. Rather surprisingly, we discover that this algorithm continues to be Bayes-consistent even in a certain infinite-dimensional setting, in which the basic measure-theoretic conditions on which classic consistency proofs hinge are violated. This is all the more surprising, since it is known that k-NN is not Bayes-consistent in this setting. We pose several challenging open problems for future research.
Original language | English |
---|---|
Pages (from-to) | 1574-1584 |
Number of pages | 11 |
Journal | Advances in Neural Information Processing Systems |
Volume | 2017-December |
State | Published - 1 Jan 2017 |
Event | 31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States Duration: 4 Dec 2017 → 9 Dec 2017 |
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing